{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T04:11:52Z","timestamp":1745381512180,"version":"3.40.4"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92267205","92067205","92367301","92267301"],"award-info":[{"award-number":["92267205","92067205","92367301","92267301"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"publisher","award":["2024-MSBA-83"],"award-info":[{"award-number":["2024-MSBA-83"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]},{"name":"State Key Laboratory of Robotics of China","award":["2023-Z15"],"award-info":[{"award-number":["2023-Z15"]}]},{"name":"National Program for Funded Postdoctoral Researchers","award":["GZB20230805"],"award-info":[{"award-number":["GZB20230805"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/lra.2025.3558648","type":"journal-article","created":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T22:09:35Z","timestamp":1744063775000},"page":"5401-5408","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Robot Learning Through Cognitive Reasoning Trajectory Optimization Under Unknown Dynamics"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6783-8647","authenticated-orcid":false,"given":"Qingwei","family":"Dong","sequence":"first","affiliation":[{"name":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6982-6994","authenticated-orcid":false,"given":"Tingting","family":"Wu","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7863-3260","authenticated-orcid":false,"given":"Peng","family":"Zeng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanzhi","family":"zang","sequence":"additional","affiliation":[{"name":"School of Artifcial Intelligence, Shenyang University of Technology, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4456-6236","authenticated-orcid":false,"given":"Guangxi","family":"Wan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3771-706X","authenticated-orcid":false,"given":"Shijie","family":"Cui","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2958211"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","year":"2023","author":"Huang","key":"ref4"},{"key":"ref5","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Proc. 6th Conf. Robot Learn.","author":"Brohan","year":"2023"},{"key":"ref6","first-page":"38154","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Shen","year":"2024"},{"key":"ref7","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wei","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref9","first-page":"1769","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Proc. Conf. Robot Learn.","author":"Huang","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4222-0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139550"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref13","first-page":"334","article-title":"Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","author":"James","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2159412"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2012.2210294"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463197"},{"key":"ref17","first-page":"47","article-title":"Deep kernels for optimizing locomotion controllers","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","author":"Antonova","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/nature14422"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1561\/2300000021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3497992"},{"key":"ref22","first-page":"11809","article-title":"Tree of thoughts: Deliberate problem solving with large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yao","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"article-title":"Plan-seq-learn: Language model guided rl for solving long horizon robotics tasks","year":"2024","author":"Dalal","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i18.30006"},{"key":"ref26","first-page":"12086","article-title":"LLM$^{3}$: Large language model-based task and motion planning with motion failure reasoning","volume-title":"Proc. IEEE\/RSJ Int. Conf. Intell. Robots Syst.","author":"Wang","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3320012"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3410155"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3400189"},{"key":"ref31","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref32","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Huang","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3333661"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354297"},{"issue":"39","key":"ref36","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref37","first-page":"28496","article-title":"Continual world: A robotic benchmark for continual reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Woczyk","year":"2021"},{"key":"ref38","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Yu","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342382"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10969146\/10955186.pdf?arnumber=10955186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T05:26:07Z","timestamp":1745299567000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10955186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":39,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3558648","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}